AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

NAS-DIP: Learning Deep Image Prior with Neural Architecture Search

Yun-Chun Chen, Chen Gao, Esther Robb, Jia-Bin Huang

ECCV 2020 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 60 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add searched cross-scale residual connections to searched upsampling (ablation)NAS-DIP · Ablation: Set14 SR 4xPSNR (dB): 27.54 -> 27.84Improved
add searched cross-scale residual connections to searched upsampling (ablation)NAS-DIP · Ablation: inpaintingPSNR (dB): 34.01 -> 34.72Improved
add searched cross-scale residual connections to searched upsampling (ablation)NAS-DIP · Ablation: denoisingPSNR (dB): 31.08 -> 31.42Improved
add searched upsampling cell to searched connections (ablation)NAS-DIP · Ablation: Set14 SR 4xPSNR (dB): 27.32 -> 27.84Improved
add searched upsampling cell to searched connections (ablation)NAS-DIP · Ablation: Set14 SR 8xPSNR (dB): 24.29 -> 24.59Improved
add searched upsampling cell to searched connections (ablation)NAS-DIP · Ablation: inpaintingPSNR (dB): 34.59 -> 34.72Improved
add searched upsampling cell to searched connections (ablation)NAS-DIP · Ablation: denoisingPSNR (dB): 31.16 -> 31.42Improved
use searched architecture instead of hand-crafted U-Net (DIP)DIP · Set14 super-resolution 4xPSNR (dB): 27.00 -> 27.84Improved
use searched architecture instead of hand-crafted U-Net (DIP)DIP · Image denoising (BM3D dataset)PSNR (dB): 30.43 -> 31.42Improved
use searched architecture instead of Deep DecoderDeep Decoder · Deep Decoder protocol: inpaintingPSNR (dB): 31.9 -> 33.1Improved
use searched model in CycleGAN instead of standard U-NetCycleGAN · Summer-to-Winter translationFID: 78.62 -> 76.22Improved
use searched model in CycleGAN instead of standard U-NetCycleGAN · Winter-to-Summer translationFID: 73.91 -> 71.98Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy